Merge branches 'perf-fixes-for-linus' and 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  jump label: Add work around to i386 gcc asm goto bug
  x86, ftrace: Use safe noops, drop trap test
  jump_label: Fix unaligned traps on sparc.
  jump label: Make arch_jump_label_text_poke_early() optional
  jump label: Fix error with preempt disable holding mutex
  oprofile: Remove deprecated use of flush_scheduled_work()
  oprofile: Fix the hang while taking the cpu offline
  jump label: Fix deadlock b/w jump_label_mutex vs. text_mutex
  jump label: Fix module __init section race

* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Check irq_remapped instead of remapping_enabled in destroy_irq()
diff --git a/arch/Kconfig b/arch/Kconfig
index 53d7f61..8bf0fa65 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -42,6 +42,20 @@
 	  for kernel debugging, non-intrusive instrumentation and testing.
 	  If in doubt, say "N".
 
+config JUMP_LABEL
+       bool "Optimize trace point call sites"
+       depends on HAVE_ARCH_JUMP_LABEL
+       help
+         If it is detected that the compiler has support for "asm goto",
+	 the kernel will compile trace point locations with just a
+	 nop instruction. When trace points are enabled, the nop will
+	 be converted to a jump to the trace function. This technique
+	 lowers overhead and stress on the branch prediction of the
+	 processor.
+
+	 On i386, options added to the compiler flags may increase
+	 the size of the kernel slightly.
+
 config OPTPROBES
 	def_bool y
 	depends on KPROBES && HAVE_OPTPROBES
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 65c0d30..427d468 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -13,6 +13,7 @@
 			 "nop\n\t"				\
 			 "nop\n\t"				\
 			 ".pushsection __jump_table,  \"a\"\n\t"\
+			 ".align 4\n\t"				\
 			 ".word 1b, %l[" #label "], %c0\n\t"	\
 			 ".popsection \n\t"			\
 			 : :  "i" (key) :  : label);\
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 1255d95..f2ee1ab 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -51,7 +51,18 @@
 # prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
 # tracer assumptions. For i686, generic, core2 this is set by the
 # compiler anyway
-cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-maccumulate-outgoing-args)
+ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
+ADD_ACCUMULATE_OUTGOING_ARGS := y
+endif
+
+# Work around to a bug with asm goto with first implementations of it
+# in gcc causing gcc to mess up the push and pop of the stack in some
+# uses of asm goto.
+ifeq ($(CONFIG_JUMP_LABEL), y)
+ADD_ACCUMULATE_OUTGOING_ARGS := y
+endif
+
+cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
 
 # Bug fix for binutils: this option is required in order to keep
 # binutils from generating NOPL instructions against our will.
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5ceeca3..5079f24 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -644,65 +644,26 @@
 
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 
-unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+#ifdef CONFIG_X86_64
+unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };
+#else
+unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
+#endif
 
 void __init arch_init_ideal_nop5(void)
 {
-	extern const unsigned char ftrace_test_p6nop[];
-	extern const unsigned char ftrace_test_nop5[];
-	extern const unsigned char ftrace_test_jmp[];
-	int faulted = 0;
-
 	/*
-	 * There is no good nop for all x86 archs.
-	 * We will default to using the P6_NOP5, but first we
-	 * will test to make sure that the nop will actually
-	 * work on this CPU. If it faults, we will then
-	 * go to a lesser efficient 5 byte nop. If that fails
-	 * we then just use a jmp as our nop. This isn't the most
-	 * efficient nop, but we can not use a multi part nop
-	 * since we would then risk being preempted in the middle
-	 * of that nop, and if we enabled tracing then, it might
-	 * cause a system crash.
+	 * There is no good nop for all x86 archs.  This selection
+	 * algorithm should be unified with the one in find_nop_table(),
+	 * but this should be good enough for now.
 	 *
-	 * TODO: check the cpuid to determine the best nop.
+	 * For cases other than the ones below, use the safe (as in
+	 * always functional) defaults above.
 	 */
-	asm volatile (
-		"ftrace_test_jmp:"
-		"jmp ftrace_test_p6nop\n"
-		"nop\n"
-		"nop\n"
-		"nop\n"  /* 2 byte jmp + 3 bytes */
-		"ftrace_test_p6nop:"
-		P6_NOP5
-		"jmp 1f\n"
-		"ftrace_test_nop5:"
-		".byte 0x66,0x66,0x66,0x66,0x90\n"
-		"1:"
-		".section .fixup, \"ax\"\n"
-		"2:	movl $1, %0\n"
-		"	jmp ftrace_test_nop5\n"
-		"3:	movl $2, %0\n"
-		"	jmp 1b\n"
-		".previous\n"
-		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
-		_ASM_EXTABLE(ftrace_test_nop5, 3b)
-		: "=r"(faulted) : "0" (faulted));
-
-	switch (faulted) {
-	case 0:
-		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
-		memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5);
-		break;
-	case 1:
-		pr_info("converting mcount calls to 66 66 66 66 90\n");
-		memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5);
-		break;
-	case 2:
-		pr_info("converting mcount calls to jmp . + 5\n");
-		memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5);
-		break;
-	}
-
+#ifdef CONFIG_X86_64
+	/* Don't use these on 32 bits due to broken virtualizers */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		memcpy(ideal_nop5, p6_nops[5], 5);
+#endif
 }
 #endif
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 0929191..7cc0a72 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3109,7 +3109,7 @@
 
 	irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
 
-	if (intr_remapping_enabled)
+	if (irq_remapped(cfg))
 		free_irte(irq);
 	raw_spin_lock_irqsave(&vector_lock, flags);
 	__clear_irq_vector(irq, cfg);
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index b7e755f..a3984f4 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -190,7 +190,7 @@
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 	task_handoff_unregister(&task_free_nb);
 	mutex_unlock(&buffer_mutex);
-	flush_scheduled_work();
+	flush_cpu_work();
 
 	/* make sure we don't leak task structs */
 	process_task_mortuary();
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index f179ac2..59f5544 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -111,14 +111,18 @@
 
 void end_cpu_work(void)
 {
-	int i;
-
 	work_enabled = 0;
+}
+
+void flush_cpu_work(void)
+{
+	int i;
 
 	for_each_online_cpu(i) {
 		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);
 
-		cancel_delayed_work(&b->work);
+		/* these works are per-cpu, no need for flush_sync */
+		flush_delayed_work(&b->work);
 	}
 }
 
diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h
index 68ea16a..e1d097e 100644
--- a/drivers/oprofile/cpu_buffer.h
+++ b/drivers/oprofile/cpu_buffer.h
@@ -25,6 +25,7 @@
 
 void start_cpu_work(void);
 void end_cpu_work(void);
+void flush_cpu_work(void);
 
 /* CPU buffer is composed of such entries (which are
  * also used for context switch notes)
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index dc0ae4d..0107251 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -21,6 +21,7 @@
 #include "oprof.h"
 
 static DEFINE_PER_CPU(struct hrtimer, oprofile_hrtimer);
+static int ctr_running;
 
 static enum hrtimer_restart oprofile_hrtimer_notify(struct hrtimer *hrtimer)
 {
@@ -33,6 +34,9 @@
 {
 	struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
 
+	if (!ctr_running)
+		return;
+
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = oprofile_hrtimer_notify;
 
@@ -42,7 +46,10 @@
 
 static int oprofile_hrtimer_start(void)
 {
+	get_online_cpus();
+	ctr_running = 1;
 	on_each_cpu(__oprofile_hrtimer_start, NULL, 1);
+	put_online_cpus();
 	return 0;
 }
 
@@ -50,6 +57,9 @@
 {
 	struct hrtimer *hrtimer = &per_cpu(oprofile_hrtimer, cpu);
 
+	if (!ctr_running)
+		return;
+
 	hrtimer_cancel(hrtimer);
 }
 
@@ -57,8 +67,11 @@
 {
 	int cpu;
 
+	get_online_cpus();
 	for_each_online_cpu(cpu)
 		__oprofile_hrtimer_stop(cpu);
+	ctr_running = 0;
+	put_online_cpus();
 }
 
 static int __cpuinit oprofile_cpu_notify(struct notifier_block *self,
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index b67cb18..7880f18 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -1,7 +1,7 @@
 #ifndef _LINUX_JUMP_LABEL_H
 #define _LINUX_JUMP_LABEL_H
 
-#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL)
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif
@@ -18,6 +18,8 @@
 extern struct jump_entry __start___jump_table[];
 extern struct jump_entry __stop___jump_table[];
 
+extern void jump_label_lock(void);
+extern void jump_label_unlock(void);
 extern void arch_jump_label_transform(struct jump_entry *entry,
 				 enum jump_label_type type);
 extern void arch_jump_label_text_poke_early(jump_label_t addr);
@@ -59,6 +61,9 @@
 	return 0;
 }
 
+static inline void jump_label_lock(void) {}
+static inline void jump_label_unlock(void) {}
+
 #endif
 
 #define COND_STMT(key, stmt)					\
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 7be868b..3b79bd9 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -39,6 +39,16 @@
 	struct module *mod;
 };
 
+void jump_label_lock(void)
+{
+	mutex_lock(&jump_label_mutex);
+}
+
+void jump_label_unlock(void)
+{
+	mutex_unlock(&jump_label_mutex);
+}
+
 static int jump_label_cmp(const void *a, const void *b)
 {
 	const struct jump_entry *jea = a;
@@ -152,7 +162,7 @@
 	struct jump_label_module_entry *e_module;
 	int count;
 
-	mutex_lock(&jump_label_mutex);
+	jump_label_lock();
 	entry = get_jump_label_entry((jump_label_t)key);
 	if (entry) {
 		count = entry->nr_entries;
@@ -168,13 +178,14 @@
 			count = e_module->nr_entries;
 			iter = e_module->table;
 			while (count--) {
-				if (kernel_text_address(iter->code))
+				if (iter->key &&
+						kernel_text_address(iter->code))
 					arch_jump_label_transform(iter, type);
 				iter++;
 			}
 		}
 	}
-	mutex_unlock(&jump_label_mutex);
+	jump_label_unlock();
 }
 
 static int addr_conflict(struct jump_entry *entry, void *start, void *end)
@@ -231,6 +242,7 @@
  * overlaps with any of the jump label patch addresses. Code
  * that wants to modify kernel text should first verify that
  * it does not overlap with any of the jump label addresses.
+ * Caller must hold jump_label_mutex.
  *
  * returns 1 if there is an overlap, 0 otherwise
  */
@@ -241,7 +253,6 @@
 	struct jump_entry *iter_stop = __start___jump_table;
 	int conflict = 0;
 
-	mutex_lock(&jump_label_mutex);
 	iter = iter_start;
 	while (iter < iter_stop) {
 		if (addr_conflict(iter, start, end)) {
@@ -256,10 +267,16 @@
 	conflict = module_conflict(start, end);
 #endif
 out:
-	mutex_unlock(&jump_label_mutex);
 	return conflict;
 }
 
+/*
+ * Not all archs need this.
+ */
+void __weak arch_jump_label_text_poke_early(jump_label_t addr)
+{
+}
+
 static __init int init_jump_label(void)
 {
 	int ret;
@@ -267,7 +284,7 @@
 	struct jump_entry *iter_stop = __stop___jump_table;
 	struct jump_entry *iter;
 
-	mutex_lock(&jump_label_mutex);
+	jump_label_lock();
 	ret = build_jump_label_hashtable(__start___jump_table,
 					 __stop___jump_table);
 	iter = iter_start;
@@ -275,7 +292,7 @@
 		arch_jump_label_text_poke_early(iter->code);
 		iter++;
 	}
-	mutex_unlock(&jump_label_mutex);
+	jump_label_unlock();
 	return ret;
 }
 early_initcall(init_jump_label);
@@ -366,6 +383,39 @@
 	}
 }
 
+static void remove_jump_label_module_init(struct module *mod)
+{
+	struct hlist_head *head;
+	struct hlist_node *node, *node_next, *module_node, *module_node_next;
+	struct jump_label_entry *e;
+	struct jump_label_module_entry *e_module;
+	struct jump_entry *iter;
+	int i, count;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return;
+
+	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
+		head = &jump_label_table[i];
+		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
+			hlist_for_each_entry_safe(e_module, module_node,
+						  module_node_next,
+						  &(e->modules), hlist) {
+				if (e_module->mod != mod)
+					continue;
+				count = e_module->nr_entries;
+				iter = e_module->table;
+				while (count--) {
+					if (within_module_init(iter->code, mod))
+						iter->key = 0;
+					iter++;
+				}
+			}
+		}
+	}
+}
+
 static int
 jump_label_module_notify(struct notifier_block *self, unsigned long val,
 			 void *data)
@@ -375,16 +425,21 @@
 
 	switch (val) {
 	case MODULE_STATE_COMING:
-		mutex_lock(&jump_label_mutex);
+		jump_label_lock();
 		ret = add_jump_label_module(mod);
 		if (ret)
 			remove_jump_label_module(mod);
-		mutex_unlock(&jump_label_mutex);
+		jump_label_unlock();
 		break;
 	case MODULE_STATE_GOING:
-		mutex_lock(&jump_label_mutex);
+		jump_label_lock();
 		remove_jump_label_module(mod);
-		mutex_unlock(&jump_label_mutex);
+		jump_label_unlock();
+		break;
+	case MODULE_STATE_LIVE:
+		jump_label_lock();
+		remove_jump_label_module_init(mod);
+		jump_label_unlock();
 		break;
 	}
 	return ret;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 99865c3..9737a76 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1145,14 +1145,13 @@
 	if (ret)
 		return ret;
 
+	jump_label_lock();
 	preempt_disable();
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr) ||
 	    ftrace_text_reserved(p->addr, p->addr) ||
-	    jump_label_text_reserved(p->addr, p->addr)) {
-		preempt_enable();
-		return -EINVAL;
-	}
+	    jump_label_text_reserved(p->addr, p->addr))
+		goto fail_with_jump_label;
 
 	/* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
 	p->flags &= KPROBE_FLAG_DISABLED;
@@ -1166,10 +1165,9 @@
 		 * We must hold a refcount of the probed module while updating
 		 * its code to prohibit unexpected unloading.
 		 */
-		if (unlikely(!try_module_get(probed_mod))) {
-			preempt_enable();
-			return -EINVAL;
-		}
+		if (unlikely(!try_module_get(probed_mod)))
+			goto fail_with_jump_label;
+
 		/*
 		 * If the module freed .init.text, we couldn't insert
 		 * kprobes in there.
@@ -1177,16 +1175,18 @@
 		if (within_module_init((unsigned long)p->addr, probed_mod) &&
 		    probed_mod->state != MODULE_STATE_COMING) {
 			module_put(probed_mod);
-			preempt_enable();
-			return -EINVAL;
+			goto fail_with_jump_label;
 		}
 	}
 	preempt_enable();
+	jump_label_unlock();
 
 	p->nmissed = 0;
 	INIT_LIST_HEAD(&p->list);
 	mutex_lock(&kprobe_mutex);
 
+	jump_label_lock(); /* needed to call jump_label_text_reserved() */
+
 	get_online_cpus();	/* For avoiding text_mutex deadlock. */
 	mutex_lock(&text_mutex);
 
@@ -1214,12 +1214,18 @@
 out:
 	mutex_unlock(&text_mutex);
 	put_online_cpus();
+	jump_label_unlock();
 	mutex_unlock(&kprobe_mutex);
 
 	if (probed_mod)
 		module_put(probed_mod);
 
 	return ret;
+
+fail_with_jump_label:
+	preempt_enable();
+	jump_label_unlock();
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(register_kprobe);